Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 643 585  51 962 849 850 817 222 334 681 141 623 337 357 667  14 990 944 417 626
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 334 643 623 626  14  NA 962 141 585 681 357  51 337 849 990 817 667  NA 944 417 850 222  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 3 2 4 3 2 4 2 3 3 1
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "m" "r" "z" "i" "n" "R" "Y" "C" "X" "G"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  4 17 18
which( manyNumbersWithNA > 900 )
[1]  7 15 19
which( is.na( manyNumbersWithNA ) )
[1]  6 18 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 962 990 944
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 962 990 944
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 962 990 944

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "R" "Y" "C" "X" "G"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "m" "r" "z" "i" "n"
manyNumbers %in% 300:600
 [1] FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE
[18] FALSE  TRUE FALSE
which( manyNumbers %in% 300:600 )
[1]  2  9 13 14 19
sum( manyNumbers %in% 300:600 )
[1] 5

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "large" "large" "large" "small" NA      "large" "small" "large" "large" "small" "small" "small"
[14] "large" "large" "large" "large" NA      "large" "small" "large" "small" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "large"   "large"   "large"   "small"   "UNKNOWN" "large"   "small"   "large"   "large"  
[11] "small"   "small"   "small"   "large"   "large"   "large"   "large"   "UNKNOWN" "large"   "small"  
[21] "large"   "small"   "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0 643 623 626   0  NA 962   0 585 681   0   0   0 849 990 817 667  NA 944   0 850   0  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 3 2 4 1
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  3  2  4  1
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 15
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 990
which.min( manyNumbersWithNA )
[1] 5
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 14
range( manyNumbersWithNA, na.rm = TRUE )
[1]  14 990

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 334 643 623 626  14  NA 962 141 585 681 357  51 337 849 990 817 667  NA 944 417 850 222  NA
sort( manyNumbersWithNA )
 [1]  14  51 141 222 334 337 357 417 585 623 626 643 667 681 817 849 850 944 962 990
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  14  51 141 222 334 337 357 417 585 623 626 643 667 681 817 849 850 944 962 990  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 990 962 944 850 849 817 681 667 643 626 623 585 417 357 337 334 222 141  51  14  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 334 643 623 626  14
order( manyNumbersWithNA[1:5] )
[1] 5 1 3 4 2
rank( manyNumbersWithNA[1:5] )
[1] 2 5 3 4 1
sort( mixedLetters )
 [1] "C" "G" "i" "m" "n" "r" "R" "X" "Y" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 2.5 1.0 9.5 7.5 6.0 4.5 9.5 7.5 2.5 4.5
rank( manyDuplicates, ties.method = "min" )
 [1] 2 1 9 7 6 4 9 7 2 4
rank( manyDuplicates, ties.method = "random" )
 [1]  2  1  9  8  6  5 10  7  3  4

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000  0.4282621 -1.2044679  0.4746821  1.7156764
[10] -1.6348784  2.6231200  0.5769743  0.5119942 -2.1176779 -0.4671653
round( v, 0 )
 [1] -1  0  0  0  1  0 -1  0  2 -2  3  1  1 -2  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.4 -1.2  0.5  1.7 -1.6  2.6  0.6  0.5 -2.1 -0.5
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.43 -1.20  0.47  1.72 -1.63  2.62  0.58  0.51 -2.12 -0.47
floor( v )
 [1] -1 -1  0  0  1  0 -2  0  1 -2  2  0  0 -3 -1
ceiling( v )
 [1] -1  0  0  1  1  1 -1  1  2 -1  3  1  1 -2  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC